Look Before You Fuse: 2D-Guided Cross-Modal Alignment for Robust 3D Detection

• URL: http://arxiv.org/abs/2507.16861v2
• Date: Thu, 07 Aug 2025 07:24:32 GMT
• Title: Look Before You Fuse: 2D-Guided Cross-Modal Alignment for Robust 3D Detection
• Authors: Xiang Li, Zhangchi Hu, Xiao Xu, Bin Kong,
• Abstract summary: Existing methods suffer from spatial misalignment between LiDAR and camera features.<n>The root cause of this misalignment lies in projection errors, stemming from calibration inaccuracies and rolling shutter effect.<n>We introduce Discontinuity Aware Geometric Fusion to suppress residual noise from PGDC and explicitly enhance sharp depth transitions at object-background boundaries.<n>Our method achieves SOTA performance on nuScenes validation dataset, with its mAP and NDS reaching 71.5% and 73.6% respectively.
• Score: 7.448164560761331
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Integrating LiDAR and camera inputs into a unified Bird's-Eye-View (BEV) representation is crucial for enhancing 3D perception capabilities of autonomous vehicles. However, existing methods suffer from spatial misalignment between LiDAR and camera features, which causes inaccurate depth supervision in camera branch and erroneous fusion during cross-modal feature aggregation. The root cause of this misalignment lies in projection errors, stemming from calibration inaccuracies and rolling shutter effect. The key insight of this work is that locations of these projection errors are not random but highly predictable, as they are concentrated at object-background boundaries which 2D detectors can reliably identify. Based on this, our main motivation is to utilize 2D object priors to pre-align cross-modal features before fusion. To address local misalignment, we propose Prior Guided Depth Calibration (PGDC), which leverages 2D priors to alleviate misalignment and preserve correct cross-modal feature pairs. To resolve global misalignment, we introduce Discontinuity Aware Geometric Fusion (DAGF) to suppress residual noise from PGDC and explicitly enhance sharp depth transitions at object-background boundaries, yielding a structurally aware representation. To effectively utilize these aligned representations, we incorporate Structural Guidance Depth Modulator (SGDM), using a gated attention mechanism to efficiently fuse aligned depth and image features. Our method achieves SOTA performance on nuScenes validation dataset, with its mAP and NDS reaching 71.5% and 73.6% respectively

Related papers

• DF-Calib: Targetless LiDAR-Camera Calibration via Depth Flow [30.56092814783138]
  DF-Calib is a LiDAR-camera calibration method that reformulates calibration as an intra-modality depth flow estimation problem.<n> DF-Calib estimates a dense depth map from the camera image and completes the sparse LiDAR projected depth map.<n>We introduce a reliability map to prioritize valid pixels and propose a perceptually weighted sparse flow loss to enhance depth flow estimation.
  arXiv  Detail & Related papers  (2025-04-02T07:09:44Z)
• Learning to Align and Refine: A Foundation-to-Diffusion Framework for Occlusion-Robust Two-Hand Reconstruction [50.952228546326516]
  Two-hand reconstruction from monocular images faces persistent challenges due to complex and dynamic hand postures.<n>Existing approaches struggle with such alignment issues, often resulting in misalignment and penetration artifacts.<n>We propose a dual-stage Foundation-to-Diffusion framework that precisely align 2D prior guidance from vision foundation models.
  arXiv  Detail & Related papers  (2025-03-22T14:42:27Z)
• Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration [20.82054596017465]
  Recent camera-based 3D object detection is limited by the precision of transforming from image to 3D feature spaces. This paper aims to address such a fundamental problem of camera-based 3D object detection: How to effectively learn depth information for accurate feature lifting and object localization.
  arXiv  Detail & Related papers  (2024-02-07T14:21:26Z)
• P2O-Calib: Camera-LiDAR Calibration Using Point-Pair Spatial Occlusion Relationship [1.6921147361216515]
  We propose a novel target-less calibration approach based on the 2D-3D edge point extraction using the occlusion relationship in 3D space. Our method achieves low error and high robustness that can contribute to the practical applications relying on high-quality Camera-LiDAR calibration.
  arXiv  Detail & Related papers  (2023-11-04T14:32:55Z)
• Multi-Sem Fusion: Multimodal Semantic Fusion for 3D Object Detection [11.575945934519442]
  LiDAR and camera fusion techniques are promising for achieving 3D object detection in autonomous driving. Most multi-modal 3D object detection frameworks integrate semantic knowledge from 2D images into 3D LiDAR point clouds. We propose a general multi-modal fusion framework Multi-Sem Fusion (MSF) to fuse the semantic information from both the 2D image and 3D points scene parsing results.
  arXiv  Detail & Related papers  (2022-12-10T10:54:41Z)
• From One to Many: Dynamic Cross Attention Networks for LiDAR and Camera Fusion [12.792769704561024]
  Existing fusion methods tend to align each 3D point to only one projected image pixel based on calibration. We propose a Dynamic Cross Attention (DCA) module with a novel one-to-many cross-modality mapping. The whole fusion architecture named Dynamic Cross Attention Network (DCAN) exploits multi-level image features and adapts to multiple representations of point clouds.
  arXiv  Detail & Related papers  (2022-09-25T16:10:14Z)
• MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection [89.26380781863665]
  Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images into 3D space for fusion. We propose a novel framework that focuses on the multi-scale progressive interaction of the multi-granularity LiDAR and camera features.
  arXiv  Detail & Related papers  (2022-09-07T12:29:29Z)
• TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers [49.689566246504356]
  We propose TransFusion, a robust solution to LiDAR-camera fusion with a soft-association mechanism to handle inferior image conditions. TransFusion achieves state-of-the-art performance on large-scale datasets. We extend the proposed method to the 3D tracking task and achieve the 1st place in the leaderboard of nuScenes tracking.
  arXiv  Detail & Related papers  (2022-03-22T07:15:13Z)
• DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection [83.18142309597984]
  Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. We develop a family of generic multi-modal 3D detection models named DeepFusion, which is more accurate than previous methods.
  arXiv  Detail & Related papers  (2022-03-15T18:46:06Z)
• SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation [98.83762558394345]
  SO-Pose is a framework for regressing all 6 degrees-of-freedom (6DoF) for the object pose in a cluttered environment from a single RGB image. We introduce a novel reasoning about self-occlusion, in order to establish a two-layer representation for 3D objects. Cross-layer consistencies that align correspondences, self-occlusion and 6D pose, we can further improve accuracy and robustness.
  arXiv  Detail & Related papers  (2021-08-18T19:49:29Z)
• LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation [78.74202673902303]
  We propose a coarse-tofine LiDAR and camera fusion-based network (termed as LIF-Seg) for LiDAR segmentation. The proposed method fully utilizes the contextual information of images and introduces a simple but effective early-fusion strategy. The cooperation of these two components leads to the success of the effective camera-LiDAR fusion.
  arXiv  Detail & Related papers  (2021-08-17T08:53:11Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• M3DSSD: Monocular 3D Single Stage Object Detector [82.25793227026443]
  We propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. The proposed M3DSSD achieves significantly better performance than the monocular 3D object detection methods on the KITTI dataset.
  arXiv  Detail & Related papers  (2021-03-24T13:09:11Z)
• Cross-Modality 3D Object Detection [63.29935886648709]
  We present a novel two-stage multi-modal fusion network for 3D object detection. The whole architecture facilitates two-stage fusion. Our experiments on the KITTI dataset show that the proposed multi-stage fusion helps the network to learn better representations.
  arXiv  Detail & Related papers  (2020-08-16T11:01:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.